impl/io/ChunkedInputStream.java

/*
 * $HeadURL: http://svn.apache.org/repos/asf/httpcomponents/httpcore/trunk/module-main/src/main/java/org/apache/http/impl/io/ChunkedInputStream.java $
 * $Revision: 569843 $
 * $Date: 2007-08-26 10:05:40 -0700 (Sun, 26 Aug 2007) $
 *
 * ====================================================================
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *   http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing,
 * software distributed under the License is distributed on an
 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 * KIND, either express or implied.  See the License for the
 * specific language governing permissions and limitations
 * under the License.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 *
 */

package org.apache.http.impl.io;

import java.io.IOException;
import java.io.InputStream;

import org.apache.http.Header;
import org.apache.http.HttpException;
import org.apache.http.MalformedChunkCodingException;
import org.apache.http.io.SessionInputBuffer;
import org.apache.http.protocol.HTTP;
import org.apache.http.util.CharArrayBuffer;
import org.apache.http.util.ExceptionUtils;

/**
 * Implements chunked transfer coding.
 * See <a href="http://www.w3.org/Protocols/rfc2616/rfc2616.txt">RFC 2616</a>,
 * <a href="http://www.w3.org/Protocols/rfc2616/rfc2616-sec3.html#sec3.6">section 3.6.1</a>.
 * It transparently coalesces chunks of a HTTP stream that uses chunked
 * transfer coding. After the stream is read to the end, it provides access
 * to the trailers, if any.
 * <p>
 * Note that this class NEVER closes the underlying stream, even when close
 * gets called.  Instead, it will read until the "end" of its chunking on
 * close, which allows for the seamless execution of subsequent HTTP 1.1
 * requests, while not requiring the client to remember to read the entire
 * contents of the response.
 * </p>
 *
 * @author Ortwin Glueck
 * @author Sean C. Sullivan
 * @author Martin Elwin
 * @author Eric Johnson
 * @author <a href="mailto:mbowler (at) GargoyleSoftware.com">Mike Bowler</a>
 * @author Michael Becke
 * @author <a href="mailto:oleg at ural.ru">Oleg Kalnichevski</a>
 *
 * @since 4.0
 *
 */
public class ChunkedInputStream extends InputStream {

    /** The session input buffer */
    private SessionInputBuffer in;

    private final CharArrayBuffer buffer;

    /** The chunk size */
    private int chunkSize;

    /** The current position within the current chunk */
    private int pos;

    /** True if we'are at the beginning of stream */
    private boolean bof = true;

    /** True if we've reached the end of stream */
    private boolean eof = false;

    /** True if this stream is closed */
    private boolean closed = false;

    private Header[] footers = new Header[] {};

    public ChunkedInputStream(final SessionInputBuffer in) {
        super();
        if (in == null) {
            throw new IllegalArgumentException("Session input buffer may not be null");
        }
        this.in = in;
        this.pos = 0;
        this.buffer = new CharArrayBuffer(16);
    }

    /**
     * <p> Returns all the data in a chunked stream in coalesced form. A chunk
     * is followed by a CRLF. The method returns -1 as soon as a chunksize of 0
     * is detected.</p>
     *
     * <p> Trailer headers are read automcatically at the end of the stream and
     * can be obtained with the getResponseFooters() method.</p>
     *
     * @return -1 of the end of the stream has been reached or the next data
     * byte
     * @throws IOException If an IO problem occurs
     */
    public int read() throws IOException {
        if (this.closed) {
            throw new IOException("Attempted read from closed stream.");
        }
        if (this.eof) {
            return -1;
        }
        if (this.pos >= this.chunkSize) {
            nextChunk();
            if (this.eof) {
                return -1;
            }
        }
        pos++;
        return in.read();
    }

    /**
     * Read some bytes from the stream.
     * @param b The byte array that will hold the contents from the stream.
     * @param off The offset into the byte array at which bytes will start to be
     * placed.
     * @param len the maximum number of bytes that can be returned.
     * @return The number of bytes returned or -1 if the end of stream has been
     * reached.
     * @see java.io.InputStream#read(byte[], int, int)
     * @throws IOException if an IO problem occurs.
     */
    public int read (byte[] b, int off, int len) throws IOException {

        if (closed) {
            throw new IOException("Attempted read from closed stream.");
        }

        if (eof) {
            return -1;
        }
        if (pos >= chunkSize) {
            nextChunk();
            if (eof) {
                return -1;
            }
        }
        len = Math.min(len, chunkSize - pos);
        int count = in.read(b, off, len);
        pos += count;
        return count;
    }

    /**
     * Read some bytes from the stream.
     * @param b The byte array that will hold the contents from the stream.
     * @return The number of bytes returned or -1 if the end of stream has been
     * reached.
     * @see java.io.InputStream#read(byte[])
     * @throws IOException if an IO problem occurs.
     */
    public int read (byte[] b) throws IOException {
        return read(b, 0, b.length);
    }

    /**
     * Read the next chunk.
     * @throws IOException If an IO error occurs.
     */
    private void nextChunk() throws IOException {
        chunkSize = getChunkSize();
        if (chunkSize < 0) {
            throw new MalformedChunkCodingException("Negative chunk size");
        }
        bof = false;
        pos = 0;
        if (chunkSize == 0) {
            eof = true;
            parseTrailerHeaders();
        }
    }

    /**
     * Expects the stream to start with a chunksize in hex with optional
     * comments after a semicolon. The line must end with a CRLF: "a3; some
     * comment\r\n" Positions the stream at the start of the next line.
     *
     * @param in The new input stream.
     * @param required <tt>true<tt/> if a valid chunk must be present,
     *                 <tt>false<tt/> otherwise.
     *
     * @return the chunk size as integer
     *
     * @throws IOException when the chunk size could not be parsed
     */
    private int getChunkSize() throws IOException {
        // skip CRLF
        if (!bof) {
            int cr = in.read();
            int lf = in.read();
            if ((cr != HTTP.CR) || (lf != HTTP.LF)) {
                throw new MalformedChunkCodingException(
                    "CRLF expected at end of chunk");
            }
        }
        //parse data
        this.buffer.clear();
        int i = this.in.readLine(this.buffer);
        if (i == -1) {
            throw new MalformedChunkCodingException(
                    "Chunked stream ended unexpectedly");
        }
        int separator = this.buffer.indexOf(';');
        if (separator < 0) {
            separator = this.buffer.length();
        }
        try {
            return Integer.parseInt(this.buffer.substringTrimmed(0, separator), 16);
        } catch (NumberFormatException e) {
            throw new MalformedChunkCodingException("Bad chunk header");
        }
    }

    /**
     * Reads and stores the Trailer headers.
     * @throws IOException If an IO problem occurs
     */
    private void parseTrailerHeaders() throws IOException {
        try {
            this.footers = AbstractMessageParser.parseHeaders
                (in, -1, -1, null);
        } catch (HttpException e) {
            IOException ioe = new MalformedChunkCodingException("Invalid footer: "
                    + e.getMessage());
            ExceptionUtils.initCause(ioe, e);
            throw ioe;
        }
    }

    /**
     * Upon close, this reads the remainder of the chunked message,
     * leaving the underlying socket at a position to start reading the
     * next response without scanning.
     * @throws IOException If an IO problem occurs.
     */
    public void close() throws IOException {
        if (!closed) {
            try {
                if (!eof) {
                    exhaustInputStream(this);
                }
            } finally {
                eof = true;
                closed = true;
            }
        }
    }

    public Header[] getFooters() {
        return (Header[])this.footers.clone();
    }

    /**
     * Exhaust an input stream, reading until EOF has been encountered.
     *
     * <p>Note that this function is intended as a non-public utility.
     * This is a little weird, but it seemed silly to make a utility
     * class for this one function, so instead it is just static and
     * shared that way.</p>
     *
     * @param inStream The {@link InputStream} to exhaust.
     * @throws IOException If an IO problem occurs
     */
    static void exhaustInputStream(final InputStream inStream) throws IOException {
        // read and discard the remainder of the message
        byte buffer[] = new byte[1024];
        while (inStream.read(buffer) >= 0) {
            ;
        }
    }

}